A comparison of differential evolution, particle swarm optimization, artificial bee colony and cuckoo search for multilevel thresholding of waste wood

by

A comparison of differential evolution, particle swarm optimization, artificial bee colony and cuckoo search for multilevel thresholding of waste wood

Sushil Kumar, Millie Pant, Amiya Kumar Ray

Indian Institute of Technology, Roorkee.

DOI:

https://doi.org/10.7494/cmms.2013.1.0422

Abstract:

The present study deals with the image segmentation of waste wood material using some popular nature inspired metaheuristics like: Differential Evolution (DE), Particle Swarm Optimization(PSO) Artificial bee Colony (ABC) and Cuckoo Search (CS). Otsu’s between class-variance and Kapur’s maximum entropy techniques are used as fitness functions. Experiments have been performed on various images and numerical results are compared. It is observed that in some cases Otsu method is giving the same performance as DE, PSO, ABC and CS. But when class size increases DE shows better results in comparison to others.

Cite as:

Kumar, S., Pant, M., & Ray, A. (2013). A comparison of differential evolution, particle swarm optimization, artificial bee colony and cuckoo search for multilevel thresholding of waste wood. Computer Methods in Materials Science, 13(1), 135 – 140. https://doi.org/10.7494/cmms.2013.1.0422

Article (PDF):

Keywords:

DE, PSO, ABC, CS, Thresholding

References: